agently-migration

Use when migrating an existing LangChain, LangGraph, LlamaIndex, or CrewAI system into Agently and mapping each source behavior to its actual request, runtime, context/storage, or TriggerFlow owner.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, well-structured migration skill that maps source semantics to Agently owners through a concrete table and sequenced method, with real one-level-deep references. The main improvement area is adding an explicit validate-fix-retry loop for the risky broad-replacement step.

Suggestions

Add an explicit validate-then-fix-then-retry loop around step 4's comparison so the migration workflow has a feedback loop for risky broad replacement.

Include one short representative before/after trace or code sketch to move actionability from 'mostly executable' to 'fully executable' for the common LangChain-request case.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's intelligence, never explains what the frameworks are, and contains no padding; every line is task-specific and earns its place.	5 / 5
Actionability	A concrete owner-map table and a 5-step method with explicit classification rules give actionable guidance; as an instruction-only skill it lacks copy-paste code, which is acceptable but keeps it below the fully-executable anchor.	4 / 5
Workflow Clarity	A clearly sequenced 5-step method includes a compare-before-broad-replacement checkpoint and Required Cautions, but for a risky migration it lacks an explicit validate-fix-retry feedback loop, so it sits just below 5.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview with a source-specific map pointing to four real, one-level-deep reference files in references/, each keyed to a source framework; navigation is clear and content is appropriately split.	5 / 5
	Total	18 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with explicit when/what guidance and named frameworks that make it highly distinctive. The only mild gap is a narrow action-verb set and a few missing synonyms, which keep specificity and trigger-term quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names four concrete source frameworks (LangChain, LangGraph, LlamaIndex, CrewAI) and six concrete Agently owner targets (request, runtime, context/storage, TriggerFlow owner); the action set is narrow (migrate/map), keeping it just below the comprehensive-coverage anchor.	4 / 5
Completeness	Explicit 'Use when migrating...' trigger plus a concrete 'what' (mapping each source behavior to its Agently owner) clearly answer both what and when with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural framework names and 'migrating' that users would actually say, but misses common synonyms like 'porting' or 'converting'; good keyword coverage with a few natural terms absent.	4 / 5
Distinctiveness Conflict Risk	Names specific source frameworks and a specific target (Agently), giving it a clear niche with distinct triggers and minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: AgentEra/Agently-Skills
Path: skills/agently-migration/SKILL.md
Commit: 5dc8d96

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.